review_design

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden, and it does disclose meaningful behavior: the review is netlist-level and identical across backends, and the backend resolution rule is spelled out ('omit it to use the active backend', 'both' mode). It stops short of stating explicitly that the call is read-only/non-mutating and of noting prerequisites such as a loaded board.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then scope, then the backend rule, then the exclusion — a sensible order with no filler. The long parenthetical enumerations of checks are dense but each item adds discriminating information, so the size is defensible rather than padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described; the description covers scope, backend selection, and the DRC boundary. Minor gaps remain for a no-annotation tool: it never states that nothing is modified and never mentions required preconditions (board/project open) or failure behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the schema types `backend` as an unconstrained nullable string, so the description is the only source of the valid values ('altium' | 'kicad'). It also defines the default behavior when omitted and the server mode ('both') that makes the parameter necessary — exactly the compensation a low-coverage schema requires.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('EDA-agnostic design review of the open board') and then enumerates the exact check families: board stats/net classes, annotation hygiene, connectivity. It explicitly carves out geometric DRC as out of scope, so an agent can separate this from clearance/courtyard tools without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operating context (operates on the open board, same review under either EDA) and an explicit exclusion ('Geometric DRC ... is separate and backend-specific'), which routes the agent to DRC tools instead. It does not name the many overlapping siblings (design_validate, design_lint_report, pcb_layout_audit, the individual audit_find_* checks), so the choice within that family is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.